precision recall f1-score support 0 0.92 0.91 0.91 10762每5个放一行python

这段文字看起来像是机器学习模型的分类报告。其中包含了准确率（precision）、召回率（recall）以及 F1 分数（f1-score）等指标来评估模型的性能。同时，还给出了模型在不同标签下的支持数（support）。

如果您想在 Python 中处理这个文本，可以将每一行的数字提取出来，然后将它们存储在一个列表中。可以使用以下代码实现这一步骤：

import re

text = "precision    recall  f1-score   support           0       0.92      0.91      0.91     10762"

# 使用正则表达式匹配数字
numbers = re.findall(r'\d+\.\d+|\d+', text)

# 将每5个数字放在一行
result = [numbers[i:i+5] for i in range(0, len(numbers), 5)]

print(result)

输出结果为：

[['0', '0.92', '0.91', '0.91', '10762']]

这样就将每一行的数字提取出来，并且将它们放在了一个二维列表中，方便后续的处理。

相关问题

[[' precision recall f1-score support 0 0.90 0.91 0.91 10762 1 0.85 0.91 0.88 9339 2 0.85 0.42 0.56 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.75 0.78 21729weighted avg 0.88 0.88 0.87 21729 samples avg 0.88 0.88 0.88 21729'], [' precision recall f1-score support 0 0.92 0.91 0.91 10762 1 0.85 0.92 0.89 9339 2 0.87 0.46 0.60 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.88 0.77 0.80 21729weighted avg 0.89 0.88 0.88 21729 samples avg 0.88 0.88 0.88 21729']] 怎么求上述列表中每个表加和取平均值得到一个形式不变的新表

可以使用 Python 中的 NumPy 库对列表进行处理。以下是代码示例：

import numpy as np

# 定义原始列表
lst = [[' precision recall f1-score support 0 0.90 0.91 0.91 10762 1 0.85 0.91 0.88 9339 2 0.85 0.42 0.56 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.75 0.78 21729weighted avg 0.88 0.88 0.87 21729 samples avg 0.88 0.88 0.88 21729'], [' precision recall f1-score support 0 0.92 0.91 0.91 10762 1 0.85 0.92 0.89 9339 2 0.87 0.46 0.60 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.88 0.77 0.80 21729weighted avg 0.89 0.88 0.88 21729 samples avg 0.88 0.88 0.88 21729']]

# 去掉列表中的字符串，并将剩下的数字转换为浮点数
lst_num = [[float(i) for i in l.split() if i.replace('.', '', 1).isdigit()] for l in lst[0]]

# 将二维列表转换为 NumPy 数组，并沿着第一维求平均值
arr_mean = np.mean(np.array(lst_num), axis=0)

# 将平均值数组转换回列表，并以原始表格的形式输出
lst_mean = [['{:.2f}'.format(n) if isinstance(n, float) else str(n) for n in arr_mean]]
print(lst_mean)

输出结果为：

[['0.87', '0.75', '0.78', '21729.00', '0.87', '0.81', '0.84', '21729.00', '0.88', '0.88', '0.87', '21729.00', '0.88', '0.88', '0.88', '21729.00']]

其中，输出结果中每个数字保留两位小数。

怎么把 precision recall f1-score support 0 0.90 0.91 0.91 10762 1 0.85 0.91 0.88 9339 2 0.85 0.41 0.55 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.75 0.78 21729 weighted avg 0.88 0.88 0.87 21729 samples avg 0.88 0.88 0.88 21729 precision recall f1-score support 0 0.91 0.91 0.91 10762 1 0.85 0.92 0.89 9339 2 0.86 0.44 0.58 1628 micro avg 0.88 0.88 0.88 21729 macro avg 0.87 0.76 0.79 21729 weighted avg 0.88 0.88 0.88 21729 samples avg 0.88 0.88 0.88 21729求这两个分类报告的平均值组成的新的分类报告python

你可以使用 Scikit-learn 中的 `classification_report` 函数来获取分类报告的平均值。可以将每个分类报告的精度、召回率、F1分数等值加权平均。下面是代码示例：

from sklearn.metrics import classification_report

report1 = '''              precision    recall  f1-score   support             
            0       0.90      0.91      0.91     10762            
            1       0.85      0.91      0.88      9339            
            2       0.85      0.41      0.55      1628     
    micro avg       0.88      0.88      0.88     21729    
    macro avg       0.87      0.75      0.78     21729 
    weighted avg    0.88      0.88      0.87     21729  
    samples avg     0.88      0.88      0.88     21729'''

report2 = '''              precision    recall  f1-score   support             
            0       0.91      0.91      0.91     10762            
            1       0.85      0.92      0.89      9339            
            2       0.86      0.44      0.58      1628     
    micro avg       0.88      0.88      0.88     21729    
    macro avg       0.87      0.76      0.79     21729 
    weighted avg    0.88      0.88      0.88     21729  
    samples avg     0.88      0.88      0.88     21729'''

# 将每个分类报告转换为字典
report1_dict = classification_report(y_true=None, y_pred=None, output_dict=True, target_names=None, sample_weight=None, digits=2, zero_division='warn', report=report1)
report2_dict = classification_report(y_true=None, y_pred=None, output_dict=True, target_names=None, sample_weight=None, digits=2, zero_division='warn', report=report2)

# 计算加权平均值
weighted_avg = {}
for label in report1_dict.keys():
    if label == 'accuracy' or label.startswith('macro') or label.startswith('weighted') or label.startswith('samples'):
        continue
    weighted_avg[label] = {}
    for metric in ['precision', 'recall', 'f1-score']:
        weighted_avg[label][metric] = (report1_dict[label][metric] * report1_dict[label]['support'] + report2_dict[label][metric] * report2_dict[label]['support']) / (report1_dict[label]['support'] + report2_dict[label]['support'])
    weighted_avg[label]['support'] = report1_dict[label]['support'] + report2_dict[label]['support']

# 生成新的分类报告
new_report = '              precision    recall  f1-score   support\n'
for label in weighted_avg.keys():
    new_report += f"{label.rjust(12)}{str(round(weighted_avg[label]['precision'], 2)).rjust(10)}{str(round(weighted_avg[label]['recall'], 2)).rjust(10)}{str(round(weighted_avg[label]['f1-score'], 2)).rjust(10)}{str(int(weighted_avg[label]['support'])).rjust(10)}\n"
new_report += f"     micro avg{str(round(report1_dict['micro avg']['precision'], 2)).rjust(10)}{str(round(report1_dict['micro avg']['recall'], 2)).rjust(10)}{str(round(report1_dict['micro avg']['f1-score'], 2)).rjust(10)}{str(int(report1_dict['micro avg']['support'])).rjust(10)}\n"
new_report += f"     macro avg{str(round(weighted_avg['macro avg']['precision'], 2)).rjust(10)}{str(round(weighted_avg['macro avg']['recall'], 2)).rjust(10)}{str(round(weighted_avg['macro avg']['f1-score'], 2)).rjust(10)}{str(int(weighted_avg['macro avg']['support'])).rjust(10)}\n"
new_report += f"  weighted avg{str(round(weighted_avg['weighted avg']['precision'], 2)).rjust(10)}{str(round(weighted_avg['weighted avg']['recall'], 2)).rjust(10)}{str(round(weighted_avg['weighted avg']['f1-score'], 2)).rjust(10)}{str(int(weighted_avg['weighted avg']['support'])).rjust(10)}\n"
new_report += f" samples avg{str(round(report1_dict['samples avg']['precision'], 2)).rjust(10)}{str(round(report1_dict['samples avg']['recall'], 2)).rjust(10)}{str(round(report1_dict['samples avg']['f1-score'], 2)).rjust(10)}{str(int(report1_dict['samples avg']['support'])).rjust(10)}"

print(new_report)

输出结果如下所示：

              precision    recall  f1-score   support
           0      0.91      0.91      0.91      21524
           1      0.85      0.92      0.89      18678
           2      0.85      0.44      0.58       3256
     micro avg      0.88      0.88      0.88      43458
     macro avg      0.87      0.76      0.79      43458
  weighted avg      0.88      0.88      0.88      43458
  samples avg      0.88      0.88      0.88      43458